Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Journal article
Title: Learning to zoom-in via learning to zoom-out: real-world super-resolution by generating and adapting degradation
Author: Sun, W.
Gong, D.
Shi, Q.
van den Hengel, A.
Zhang, Y.
Citation: IEEE Transactions on Image Processing, 2021; 30:1-16
Publisher: Institute of Electrical and Electronics Engineers
Issue Date: 2021
ISSN: 1057-7149
Statement of
Wei Sun, Dong Gong, Qinfeng Shi, Anton van den Hengel and Yanning Zhang
Abstract: Most learning-based super-resolution (SR) methods aim to recover high-resolution (HR) image from a given low-resolution (LR) image via learning on LR-HR image pairs. The SR methods learned on synthetic data do not perform well in real-world, due to the domain gap between the artificially synthesized and real LR images. Some efforts are thus taken to capture real-world image pairs. However, the captured LR-HR image pairs usually suffer from unavoidable misalignment, which hampers the performance of end-to-end learning. Here, focusing on the real-world SR, we ask a different question: since misalignment is unavoidable, can we propose a method that does not need LR-HR image pairing and alignment at all and utilizes real images as they are? Hence we propose a framework to learn SR from an arbitrary set of unpaired LR and HR images and see how far a step can go in such a realistic and “unsupervised” setting. To do so, we firstly train a degradation generation network to generate realistic LR images and, more importantly, to capture their distribution (i.e., learning to zoom out). Instead of assuming the domain gap has been eliminated, we minimize the discrepancy between the generated data and real data while learning a degradation adaptive SR network (i.e., learning to zoom in). The proposed unpaired method achieves state-of-the-art SR results on real-world images, even in the datasets that favour the paired-learning methods more
Keywords: Super resolution (SR); domain adaptation; unpaired learning
Rights: © 2021 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.
DOI: 10.1109/TIP.2021.3049951
Published version:
Appears in Collections:Aurora harvest 4
Computer Science publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.